跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

claude-handoff

Orchestrates read-only investigation or implementation within the current session after explicit plan approval. Task-handoff instead writes a decision-complete file for a fresh, separate session — use it for work continuing later or elsewhere; use an in-session handoff to implement an approved plan now.

PaulRBerg · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add PaulRBerg/agent-skills --skill claude-handoff

技能说明


argument-hint: "[task]" compatibility: Requires Claude Code Agent-tool subagents with access to the selected model. disable-model-invocation: true metadata: install-targets: claude-code name: claude-handoff skill-dependencies:

  • agents-brain
  • code-polish
  • commit description: Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.

Claude Handoff

Orchestrates read-only investigation or implementation within the current session after explicit plan approval. Task-handoff instead writes a decision-complete file for a fresh, separate session — use it for work continuing later or elsewhere; use an in-session handoff to implement an approved plan now.

If these instructions are already present from a slash or dollar invocation, follow them directly; do not invoke this skill again through a skill tool.

Follow the Contract, then use Claude Code's in-session Agent workflow to research during planning and implement the approved plan.

Contract

  • Run only after explicit user invocation. Classify a task research-only when its requested outcome is findings, evidence, or an assessment, with no repository changes or implementation plan requested. All handoffs may run in any host mode; implementation handoffs must pass through the Plan Phase and receive explicit user approval before launch.
  • Claude owns decisions, the final plan, and orchestration. Delegate investigation to read-only research subagents only when task and repository evidence make it useful before planning.
  • Research agents gather evidence and report findings; never edit files, decide design, or return plans.
  • Implementation agents implement their assigned part of the approved plan — inspect, edit, validate — never redesign or return another plan.
  • Use the smallest effective team (one agent is valid); add agents only when decomposition materially improves latency, correctness, or verification. Never exceed eight implementation agents per handoff.
  • Size every brief before finalizing the team: estimate wall-clock time and split anything likely to exceed roughly 25-30 minutes into parallel disjoint scopes or dependency waves, adding an integration agent as needed.
  • Use at most three research agents, stable IDs R1-R3, counted separately from the eight implementation agents.
  • Keep Claude's own work to orchestration, integrity checks, failure handling, and conditional polish passes.
  • Let Claude Code choose foreground or background delivery; never pass run_in_background to the Agent tool. Only a direct terminal result or error, or a later completion or failure notification, settles an agent — a launch acknowledgement, native task row, quiet period, or surfaced permission prompt does not. Reconcile a wave only after every required terminal outcome arrives.
  • Treat an explicit user model preference (e.g. Sonnet, Opus) as an orchestration constraint on every research and implementation agent unless scoped narrower — never substitute complexity-based selection. If the Agent tool cannot launch that model, report the incompatibility and ask before falling back.
  • Treat the approved outcome, not the initial manifest or its write scopes, as the authorization boundary: when implementation reveals a related in-repository fix or evidence change the outcome requires, Claude may extend the handoff and launch follow-on agents without asking again. The discovering subagent still stops at its assigned scope and returns evidence; Claude owns scope expansion, coordination, and delegation.

Use $ARGUMENTS as the task when present; otherwise the active user request. A task naming another skill follows Companion Skills.

Companion Skills

A task that names another skill alongside this handoff — for example, run $fresh-eyes-sweep and delegate the implementation — is a composition: the companion skill defines the work; this handoff owns delegation mechanics.

  • Load the companion skill and run its discovery, judgment, and planning phases in Claude. Route read-only discovery through this skill's research agents when materially faster, then fold the companion's method, findings, and constraints into the handoff plan.
  • This contract overrides the companion's overlapping plan approval, agent limits and stable IDs, single validation owner, result fields, failure classification, commit ownership, and completion reporting, even when the companion prescribes its own subagent, validation, or commit mechanics. Its user-decision gates still bind; this skill's plan approval satisfies coincident gates, and a plan-only companion implements only when the combined invocation requested implementation and the user approved the plan.
  • Agents cannot load skills. Never brief one to "use skill X" by name; inline the specific companion instructions, conventions, or excerpts it needs.
  • A companion requirement to run $code-polish or $agents-brain polish marks that pass required in the Plan Phase; it still runs once, per Completion. Companion commit instructions never add commits.
  • Satisfy both contracts at Completion: produce the companion's required report artifacts (ledgers, tables, verdicts) alongside the completion report.

Research Phase

For a research-only task, launch one to three research agents and stop after returning the consolidated investigation; never enter the Plan Phase or launch implementation agents. For an implementation handoff, trigger research when scope is uncertain, the task crosses multiple or unfamiliar subsystems, or serial evidence-gathering would be materially slower. Zero research agents is the default for implementation handoffs. Claude alone decides the count from task and repository evidence; never ask the user to opt in or name agents.

When triggered, assign up to three agents stable IDs R1-R3 and launch immediately via the Agent tool with subagent_type: "Explore" and `model: "

阅读完整来源 ↗